20.500.12556/DKUM-13995 MODELIRANJE INDEKSA AKTIVNOSTI S STATISTIKAMI VIŠJIH REDOV ZA VREDNOTENJE REDKIH IMPULZNIH IZVOROV V KONVOLUTIVNIH MEŠANICAH MODELLING ACTIVITY INDEX WITH HIGHER-ORDER STATISTICS FOR EVALUATION OF IMPULSE SOURCES IN CONVOLUTIVE MIXTURES V doktorski disertaciji se ukvarjamo z vrednotenjem redkih impulznih izvorov v linearnih konvolutivnih mešanicah, tj. z ocenjevanjem njihovega števila, dolžin njihovih impulznih odzivov in njihovih medsebojnih prekrivanj. V ta namen razvijemo statistične modele indeksa aktivnosti, in sicer modele povprečja, variance in avtokovariančnega zaporedja, s pomočjo katerih lahko ocenimo dolžino sistemskih odzivov in število aktivnih impulznih izvorov v opazovanih signalnih mešanicah. Začnemo s pregledom obstoječega stanja na področju ocenjevanja števila izvorov in dolžine sistemskih odzivov. Nato predstavimo model konvolutivnih mešanic odzivov redkih impulznih izvorov. Na kratko predstavimo še dekompozicijo površinskih EMG, metodo kompenzacije konvolutivnih jeder in indeks aktivnosti. Pri modeliranju indeksa aktivnosti se osredotočimo ločeno na prispevke izvorov in šuma, dodanega signalom. Lastnosti razvitih modelov uporabimo pri ocenjevanju dolžine sistemskih odzivov in števila izvorov, za kar razvijemo dva postopka. Prvi temelji na modelu variance indeksa aktivnosti in s pomočjo redukcije iskalnega prostora ocenjuje tako dolžino odzivov kot tudi število izvorov. Drugi postopek je kombiniran in temelji na modelu avtokovariančnega zaporedja indeksa aktivnosti, s katerim ocenimo dolžine sistemskih odzivov. Ko so dolžine odzivov ocenjene, lahko ocenimo število izvorov s pomočjo metod za ocenjevanje števila izvorov v multiplikativnih mešanicah. Drugi pristop se je izkazal za boljšega. V nadaljevanju predstavimo še možnosti nadgradnje indeksa aktivnosti s statistikami 3. in 4. reda ter probleme, ki pri tem nastanejo. Razvite modele nato preverimo na umetnih signalih z naključnimi sistemskimi odzivi in na umetnih površinskih elektromiogramih. In this doctoral thesis, we address the evaluation of sparse impulse sources in convolutive signal mixtures. We develop statistical models of activity index, namely model of activity index average, variance and autocovariance sequence. The models can be used for the estimation of the system response lengths and the number of active impulse sources in the observed convolutive mixtures. We begin with an overview of the state of the art in the field of estimation of the number of sources and the length of system responses. Next, a model of convolutive mixtures of sparse impulse sources is introduced, which means a basis for all the derived activity index models. Next, a decomposition of surface EMG and the convolution kernel compensation (CKC) method are briefly presented. This is because activity index was introduced together with this decomposition method and it represents an essential part of CKC. The main part of this work is devoted to modelling the activity index. When doing this, we focus on the contributions of sources and noise separately. Developed models can be used for the estimation of system response lengths and the number of active impulse sources. For this purpose we developed two methods. The first one is based on the model of activity index variance and estimates the length of system responses and the number of sources by a reduction of search space. The second approach is based on the autocovariance sequence of activity index, which also estimates the length of the system responses. When the length of the system responses is estimated, the number of sources can be derived by using methods that rely on the system eigenvalues. The second approach has proved to be better. In the sequel, the possibilities for upgrading the activity index with higher-order statistics are presented. We address third- and fourth-order statistics and problems that appear when using them to extend the basic form of activity index. The developed models are verified on synthetic convolutive mixtures of sparse impulse sources. obdelava signalov sestavljeni signali konvolutivne mešanice sistem MIMO impulzni izvori ocenjevanje števila izvorov indeks aktivnosti korelacijska matrika naddoločene mešanice signalov večkanalni signali statistike višjih redov momenti višjih redov Tihonova regularizacija površinski elektromiogram matematično upanje varianca avtokovariančno zaporedje signal processing compound signals convolutive signal mixtures estimation of the number of sources activity index correlation matrix overdetermined signal mixtures array sensors surface EMG multichannel signals MIMO systems true true false [R. Istenič] Slovenski jezik Angleški jezik Doktorska disertacija 2010-05-18 11:36:36 2010-05-21 09:27:08 2022-04-12 11:39:04 2023-12-17 03:06:53 2010 0 Maribor 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.41:004.93(043.3) 14110486 URN:SI:UM:DK:WJBNEDPF DR_Istenic_Rok_2010.pdf DR_Istenic_Rok_2010.pdf 1 B4E34E747D4FAD45B3F13EAD8B3C4181 696a086564b8ed58e944aace265338aa0963d58f139f8e812bd6cbb5ac865e3d 0bbb74be-7c04-11eb-bb7a-00155d0001ca 20.500.12556/dkum/2fd5659a-f413-401e-8144-de6310f45c57 https://dk.um.si/Dokument.php?lang=slv&id=14670 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0